Giter Club home page Giter Club logo

cer3brum's Introduction

Hello There ๐Ÿ‘€

Hello There!

My name is Dennis. I am a passionate researcher, coder and Linux enthusiast trying to build software to accelerate AI solutions into clinical practice ๐Ÿค– ๐Ÿฅ

I obtained my BSc degree in Electronics and Telecommunication Engineering and my MSc degree (with a focus on Signal Processing) at the University of Brescia, Italy, where I was born and raised ๐Ÿ‡ฎ๐Ÿ‡น

After my Master Degree, I worked in a multidisciplinary group between Glasgow, Scotland ๐Ÿด๓ ง๓ ข๓ ณ๓ ฃ๓ ด๓ ฟ and my hometown to develop AI pipelines for Brain MRI segmentation. Throughout this wonderful experience I was supervised by my colleague (and friend!) @rockNroll87q.


๐ŸŒฑ What Do I Do

Currently, I am a research scholar at the Harvard's AIM Program ๐Ÿ‡บ๐Ÿ‡ธ and a Ph.D. Student at Maastricht University ๐Ÿ‡ณ๐Ÿ‡ฑ

My research focuses on AI applied to clinical and medical imaging data (such as CT, MRI, and X-Ray), especially in the fields of radiology, radiation oncology and cardiology. During my Ph.D., I developed a profound interest in open source, open science and reproducible research. This interest eventually led me and a few colleagues sharing the open source values to the development of MHub.ai - a platform that aims to revolutionize the dissemination of AI models in medical imaging by providing meticulously curated, optimized, and portable AI-based imaging pipelines, empowering researchers with reproducible science and cutting-edge advancements in the field.

In keeping with this theme, I am also part of the NCI's Imaging Data Commons team, where I work on integrating AI-based medical image analysis pipelines into the platform and harnessing the power of the cloud for reproducible research.

You can take a look at my most recent public commits ๐Ÿ‘‰ here! ๐Ÿ‘จโ€๐Ÿ’ป

On my GitHub you can also find random repositories forked or created typically while trying to learn something off-work.


๐Ÿ“ซ You Can Reach Me at

  • ๐Ÿ“ง dbontempi [at] bwh [dot] harvard [dot] edu
  • ๐ŸŒ denbonte [dot] me

cer3brum's People

Contributors

denbonte avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar

cer3brum's Issues

CPU compatibility

Hi,

I read your paper earlier this year and I am excited to see that the code is finally available! Great work!

The notebook is very clear but I got an error message when I tried to run training.ipynb on my local CPU:
RuntimeError: /job:localhost/replica:0/task:0/device:GPU:0 unknown device.

Does current notebook support CPU? If so, how could I modify the code to make it run on CPU? Thanks so much for your help!

InvalidArgumentError: slice index 7 of dimension 4 out of bounds.

Hi,

I used Colab GPU to train the model now but I encountered another issue:

InvalidArgumentError: slice index 7 of dimension 4 out of bounds. for '{{node metrics_1/average_dice_coef_multilabel/strided_slice_16}} = StridedSlice[Index=DT_INT32, T=DT_FLOAT, begin_mask=15, ellipsis_mask=0, end_mask=15, new_axis_mask=0, shrink_axis_mask=16](main_output_1/truediv, metrics_1/average_dice_coef_multilabel/strided_slice_16/stack, metrics_1/average_dice_coef_multilabel/strided_slice_16/stack_1, metrics_1/average_dice_coef_multilabel/strided_slice_16/stack_2)' with input shapes: [?,256,320,320,7], [5], [5], [5] and with computed input tensors: input[1] = <0 0 0 0 7>, input[2] = <0 0 0 0 8>, input[3] = <1 1 1 1 1>.

Have you ever seen this issue by any chance? My modified notebook and full error message can be found here:
https://github.com/SucyLi/CER3BRUM/blob/master/src/CEREBRUM_notebook_training_colab.ipynb

Thanks so much for your help!

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.